Hasil untuk "Dermatology"

M. Lewis‐Jones, A. Finlay

M. Basra, R. Fenech, R. Gatt et al.

P. Mease, D. Gladman, K. Papp et al.

Zhixiang Lu, Shijie Xu, Kaicheng Yan et al.

The deployment of vision-language models (VLMs) in dermatology is hindered by the trilemma of high computational costs, extreme data scarcity, and the black-box nature of deep learning. To address these challenges, we present SkinCLIP-VL, a resource-efficient framework that adapts foundation models for trustworthy skin cancer diagnosis. Adopting a frozen perception, adaptive reasoning paradigm, we integrate a frozen CLIP encoder with a lightweight, quantized Qwen2.5-VL via low-rank adaptation (LoRA). To strictly align visual regions with clinical semantics under long-tailed distributions, we propose the Consistency-aware Focal Alignment (CFA) Loss. This objective synergizes focal re-weighting, semantic alignment, and calibration. On ISIC and Derm7pt benchmarks, SkinCLIP-VL surpasses 13B-parameter baselines by 4.3-6.2% in accuracy with 43% fewer parameters. Crucially, blinded expert evaluation and out-of-distribution testing confirm that our visually grounded rationales significantly enhance clinical trust compared to traditional saliency maps.

Mariona Oliver, MD, Jannik Rousel, PhD, Jan W. Schoones, MSc et al.

Sonali Sharma, Ahmed M. Alaa, Roxana Daneshjou

Generative AI models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used to interpret medical images and answer clinical questions. Their responses often include inaccuracies; therefore, safety measures like medical disclaimers are critical to remind users that AI outputs are not professionally vetted or a substitute for medical advice. This study evaluated the presence of disclaimers in LLM and VLM outputs across model generations from 2022 to 2025. Using 500 mammograms, 500 chest X-rays, 500 dermatology images, and 500 medical questions, outputs were screened for disclaimer phrases. Medical disclaimer presence in LLM and VLM outputs dropped from 26.3% in 2022 to 0.97% in 2025, and from 19.6% in 2023 to 1.05% in 2025, respectively. By 2025, the majority of models displayed no disclaimers. As public models become more capable and authoritative, disclaimers must be implemented as a safeguard adapting to the clinical context of each output.

Nusrat Munia, Abdullah-Al-Zubaer Imran

Artificial Intelligence (AI) in skin disease diagnosis has improved significantly, but a major concern is that these models frequently show biased performance across subgroups, especially regarding sensitive attributes such as skin color. To address these issues, we propose a novel generative AI-based framework, namely, Dermatology Diffusion Transformer (DermDiT), which leverages text prompts generated via Vision Language Models and multimodal text-image learning to generate new dermoscopic images. We utilize large vision language models to generate accurate and proper prompts for each dermoscopic image which helps to generate synthetic images to improve the representation of underrepresented groups (patient, disease, etc.) in highly imbalanced datasets for clinical diagnoses. Our extensive experimentation showcases the large vision language models providing much more insightful representations, that enable DermDiT to generate high-quality images. Our code is available at https://github.com/Munia03/DermDiT

Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker et al.

In recent years, high-performance computer vision models have achieved remarkable success in medical imaging, with some skin lesion classification systems even surpassing dermatology specialists in diagnostic accuracy. However, such models are computationally intensive and large in size, making them unsuitable for deployment on edge devices. In addition, strict privacy constraints hinder centralized data management, motivating the adoption of Federated Learning (FL). To address these challenges, this study proposes a skewness-guided pruning method that selectively prunes the Multi-Head Self-Attention and Multi-Layer Perceptron layers of a multimodal Swin Transformer based on the statistical skewness of their output distributions. The proposed method was validated in a horizontal FL environment and shown to maintain performance while substantially reducing model complexity. Experiments on the compact Swin Transformer demonstrate approximately 36\% model size reduction with no loss in accuracy. These findings highlight the feasibility of achieving efficient model compression and privacy-preserving distributed learning for multimodal medical AI on edge devices.

Chenyang Zang, MD, Zheng Xiao, MD, Luo Zhou, MD

A. Taieb, A. Alomar, M. Böhm et al.

Ifeoma Veronica Nwabufo, Jan Niklas Böhm, Philipp Berens et al.

Self-supervised learning methods based on data augmentations, such as SimCLR, BYOL, or DINO, allow obtaining semantically meaningful representations of image datasets and are widely used prior to supervised fine-tuning. A recent self-supervised learning method, $t$-SimCNE, uses contrastive learning to directly train a 2D representation suitable for visualisation. When applied to natural image datasets, $t$-SimCNE yields 2D visualisations with semantically meaningful clusters. In this work, we used $t$-SimCNE to visualise medical image datasets, including examples from dermatology, histology, and blood microscopy. We found that increasing the set of data augmentations to include arbitrary rotations improved the results in terms of class separability, compared to data augmentations used for natural images. Our 2D representations show medically relevant structures and can be used to aid data exploration and annotation, improving on common approaches for data visualisation.

Lin Yang, Shawn Xu, Andrew Sellergren et al.

Many clinical tasks require an understanding of specialized data, such as medical images and genomics, which is not typically found in general-purpose large multimodal models. Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histopathology, ophthalmology, dermatology and genomic data. Med-Gemini-2D sets a new standard for AI-based chest X-ray (CXR) report generation based on expert evaluation, exceeding previous best results across two separate datasets by an absolute margin of 1% and 12%, where 57% and 96% of AI reports on normal cases, and 43% and 65% on abnormal cases, are evaluated as "equivalent or better" than the original radiologists' reports. We demonstrate the first ever large multimodal model-based report generation for 3D computed tomography (CT) volumes using Med-Gemini-3D, with 53% of AI reports considered clinically acceptable, although additional research is needed to meet expert radiologist reporting quality. Beyond report generation, Med-Gemini-2D surpasses the previous best performance in CXR visual question answering (VQA) and performs well in CXR classification and radiology VQA, exceeding SoTA or baselines on 17 of 20 tasks. In histopathology, ophthalmology, and dermatology image classification, Med-Gemini-2D surpasses baselines across 18 out of 20 tasks and approaches task-specific model performance. Beyond imaging, Med-Gemini-Polygenic outperforms the standard linear polygenic risk score-based approach for disease risk prediction and generalizes to genetically correlated diseases for which it has never been trained. Although further development and evaluation are necessary in the safety-critical medical domain, our results highlight the potential of Med-Gemini across a wide range of medical tasks.

Shang-Jui Kuo, Po-Han Huang, Chia-Ching Lin et al.

Diabetic foot ulcers pose health risks, including higher morbidity, mortality, and amputation rates. Monitoring wound areas is crucial for proper care, but manual segmentation is subjective due to complex wound features and background variation. Expert annotations are costly and time-intensive, thus hampering large dataset creation. Existing segmentation models relying on extensive annotations are impractical in real-world scenarios with limited annotated data. In this paper, we propose a cross-domain augmentation method named TransMix that combines Augmented Global Pre-training AGP and Localized CutMix Fine-tuning LCF to enrich wound segmentation data for model learning. TransMix can effectively improve the foot ulcer segmentation model training by leveraging other dermatology datasets not on ulcer skins or wounds. AGP effectively increases the overall image variability, while LCF increases the diversity of wound regions. Experimental results show that TransMix increases the variability of wound regions and substantially improves the Dice score for models trained with only 40 annotated images under various proportions.

Leon-Paul Schaub Torre, Pelayo Quiros, Helena Garcia Mieres

In this paper we present a hybrid method for the automatic detection of dermatological pathologies in medical reports. We use a large language model combined with medical ontologies to predict, given a first appointment or follow-up medical report, the pathology a person may suffer from. The results show that teaching the model to learn the type, severity and location on the body of a dermatological pathology, as well as in which order it has to learn these three features, significantly increases its accuracy. The article presents the demonstration of state-of-the-art results for classification of medical texts with a precision of 0.84, micro and macro F1-score of 0.82 and 0.75, and makes both the method and the data set used available to the community.

Sribala Vidyadhari Chinta, Zichong Wang, Avash Palikhe et al.

Artificial intelligence (AI) is rapidly advancing in healthcare, enhancing the efficiency and effectiveness of services across various specialties, including cardiology, ophthalmology, dermatology, emergency medicine, etc. AI applications have significantly improved diagnostic accuracy, treatment personalization, and patient outcome predictions by leveraging technologies such as machine learning, neural networks, and natural language processing. However, these advancements also introduce substantial ethical and fairness challenges, particularly related to biases in data and algorithms. These biases can lead to disparities in healthcare delivery, affecting diagnostic accuracy and treatment outcomes across different demographic groups. This review paper examines the integration of AI in healthcare, highlighting critical challenges related to bias and exploring strategies for mitigation. We emphasize the necessity of diverse datasets, fairness-aware algorithms, and regulatory frameworks to ensure equitable healthcare delivery. The paper concludes with recommendations for future research, advocating for interdisciplinary approaches, transparency in AI decision-making, and the development of innovative and inclusive AI applications.

Dimitrios P. Panagoulias, Persephone Papatheodosiou, Anastasios P. Palamidas et al.

Large Language Models (LLMs) constitute a breakthrough state-of-the-art Artificial Intelligence (AI) technology which is rapidly evolving and promises to aid in medical diagnosis either by assisting doctors or by simulating a doctor's workflow in more advanced and complex implementations. In this technical paper, we outline Cognitive Network Evaluation Toolkit for Medical Domains (COGNET-MD), which constitutes a novel benchmark for LLM evaluation in the medical domain. Specifically, we propose a scoring-framework with increased difficulty to assess the ability of LLMs in interpreting medical text. The proposed framework is accompanied with a database of Multiple Choice Quizzes (MCQs). To ensure alignment with current medical trends and enhance safety, usefulness, and applicability, these MCQs have been constructed in collaboration with several associated medical experts in various medical domains and are characterized by varying degrees of difficulty. The current (first) version of the database includes the medical domains of Psychiatry, Dentistry, Pulmonology, Dermatology and Endocrinology, but it will be continuously extended and expanded to include additional medical domains.

Shuai Li, Xiaoguang Ma, Shancheng Jiang et al.

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC.

Hua Feng, Shuxian Shang, Kun Chen et al.

BackgroundThere is evidence of a modest reduction in skin cancer risk among metformin users. However, no studies have further examined the effects of metformin on melanoma survival and safety outcomes. This study aimed to quantitatively summarize any influence of metformin on the overall survival (OS) and immune-related adverse effects (irAEs) in melanoma patients.MethodsSelection criteria: The inclusion criteria were designed based on the PICOS principles. Information sources: PubMed, EMBASE, Cochrane Library, and Web of Science were searched for relevant literature published from the inception of these databases until November 2023 using ‘Melanoma’ and ‘Metformin’ as keywords. Survival outcomes were OS, progression-free survival (PFS), recurrence-free survival (RFS), and mortality; the safety outcome was irAEs. Risk of bias and data Synthesis: The Cochrane tool for assessing the risk of bias in randomized trial 2 (RoB2) and methodological index for non-randomized studies (MINORS) were selected to assess the risk of bias. The Cochrane Q and I2 statistics based on Stata 15.1 SE were used to test the heterogeneity among all studies. Funnel plot, Egger regression, and Begg tests were used to evaluate publication bias. The leave-one-out method was selected as the sensitivity analysis tool.ResultsA total of 12 studies were included, involving 111,036 melanoma patients. The pooled HR for OS was 0.64 (95% CI [0.42, 1.00], p = 0.004, I2 = 73.7%), HR for PFS was 0.89 (95% CI [0.70, 1.12], p = 0.163, I2 = 41.4%), HR for RFS was 0.62 (95% CI [0.26, 1.48], p = 0.085, I2 = 66.3%), and HR for mortality was 0.53 (95% CI [0.46, 0.63], p = 0.775, I2 = 0.0%). There was no significant difference in irAEs incidence (OR = 1.01; 95% CI [0.42, 2.41]; p = 0.642) between metformin and no metformin groups.DiscussionThe improvement in overall survival of melanoma patients with metformin may indirectly result from its diverse biological targets and beneficial effects on multiple systemic diseases. While we could not demonstrate a specific improvement in the survival of melanoma patients, the combined benefits and safety of metformin for patients taking the drug are worthy of recognition.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/, identifier CRD42024518182.

Dong-Wei Zhang, Dong-Wei Zhang, Dong-Wei Zhang et al.

The prevalence rate of acute respiratory distress syndrome (ARDS) is estimated at approximately 10% in critically ill patients worldwide, with the mortality rate ranging from 17% to 39%. Currently, ARDS mortality is usually higher in patients with COVID-19, giving another challenge for ARDS treatment. However, the treatment efficacy for ARDS is far from satisfactory. The relationship between the gut microbiota and ARDS has been substantiated by relevant scientific studies. ARDS not only changes the distribution of gut microbiota, but also influences intestinal mucosal barrier through the alteration of gut microbiota. The modulation of gut microbiota can impact the onset and progression of ARDS by triggering dysfunctions in inflammatory response and immune cells, oxidative stress, cell apoptosis, autophagy, pyroptosis, and ferroptosis mechanisms. Meanwhile, ARDS may also influence the distribution of metabolic products of gut microbiota. In this review, we focus on the impact of ARDS on gut microbiota and how the alteration of gut microbiota further influences the immune function, cellular functions and related signaling pathways during ARDS. The roles of gut microbiota-derived metabolites in the development and occurrence of ARDS are also discussed.

P. Mattei, K. Corey, A. Kimball